Design of an efficient communication infrastructure for highly contended locks in many-core CMPs

Lock synchronization is a key programming primitive for shared-memory many-core CMPs. However, as the number of cores increases, conventional software implementations cannot meet the desirable levels of performance and scalability. Meanwhile, most existing hardware-supported lock proposals require modifications at some level of the memory hierarchy, thus degrading QoS of applications through synchronization traffic.In this paper, we propose GLock, a dedicated network infrastructure and a token-based message-passing protocol to provide a non-intrusive, extremely efficient and fair implementation for highly contended locks. Two implementations of GLock are considered. The first leverages current full-custom G-lines technology, whilst the second uses a cost-effective mainstream industrial toolflow with an advanced 45 nm technology. When compared with the most efficient software-based lock, both alternatives provide significant reductions in execution time, network traffic and power consumption, for a representative set of benchmarks, with negligible area overhead.

► Lock contention is a key constraint to performance and scalability on many-core CMPs.
► We propose GLock, a new hardware-supported implementation for highly contended locks.
► We evaluate two implementations: G-lines-based GLock and Standard-based GLock.
► Both GLocks report extremely superior efficiency against the best SW-based lock.
► GLock is not so dependent on a full-custom technology to achieve such improvements.